Agent skills

Workflow & Productivity skills

Read straight from the source repositories, not from submitted listings. Every skill shows what it does, what is inside, where it came from — and whether attention around its source is actually growing.

Toolclaude-code 29,140codex 4,755cursor 3,111copilot 976windsurf 55cline 34
CategoryWorkflow & Productivity 4,979AI & Agents 3,037Data & Analytics 2,345Code Review & Quality 1,376Backend & API 1,244Security 1,194Design & Presentation 1,154Documentation 965Content & Marketing 916Testing & QA 777DevOps & Cloud 576Databases 550Frontend 469Business & Finance 328Media & Video 257Other 9,833
11,684 found
673720 · page 15 / 244
obsidian-webhooks-eventsHandle Obsidian events and workspace callbacks for plugin development. Use when implementing reactive features, handling file…jeremylongshorewritesod-defaultHidden fallback scenario for free-form Home prompts. Infer the task type and ask only when routing is materially ambiguous.nexu-ioopenclaw-history-ingestIngest OpenClaw agent history into the Obsidian wiki. Use this skill when the user wants to mine their past OpenClaw sessions for…Ar9avopenloomi-connectorsopenloomi Connectors tools - manage the native 7 messaging integrations and pair with the composio skill for the 1000+ apps OAuth…melandlabsoraclecloud-core-workflow-aLaunch, manage, and scale OCI compute instances with capacity retry logic. Use when provisioning VMs, selecting instance shapes…jeremylongshorewritesoraclecloud-local-dev-loopSet up a productive local OCI development workflow using CLI and SDK instead of the web console. Use when the OCI Console is too…jeremylongshorewritesfull-output-enforcementOverrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit…nexu-iopaper-analyzer自动分析Zotero库中的文献,生成带LaTeX公式的Markdown报告,使用Auto-Annotation工具将AI的深度见解以无损批注形式注入回 Zotero,并将报告上传为Zotero Note。majiayu000paper-finderDiscover recent arXiv papers matching a research profile and generate Obsidian-compatible Markdown notes. Use this skill when the…majiayu000patch-editApply one rewrite-plan step at a time as small reviewable file edits, never rewriting whole files when a localised change…nexu-iopattern-recognitionConjecture generation, sequence analysis, and experimental mathematics for mathematical discovery. Covers sequence analysis (OEIS…majiayu000pay-stub-decoderDecode a pay stub line by line — every deduction explained, the gross-to-net story, and the errors worth catching. Use when asked…mohitagw15856gsd-phase-researcherResearches phase implementation for planning. Spawned by /gsd:plan-phase or /gsd:research-phase orchestrators.majiayu000phx-introWalk through the Elixir/Phoenix plugin commands, workflow, and features in 6 interactive sections. Use when a new user wants to…oliver-kriskapick-my-brainUse when starting a new task, feature, or project where the user has domain knowledge the agent lacks, before planning sessions…majiayu000plan-agentPlanning agent that creates implementation plans and handoffs from conversation contextmajiayu000plan-agentPlanning agent that creates implementation plans and handoffs from conversation contextmajiayu000plan-mode-aegis-v25-developmentAEGIS v2.5開発の包括的Planモード。数学データ収集、形式証明環境構築、GRPO訓練パイプライン、MCP/A2Aエージェント開発、進捗監視を実装。SO(8)四重推論再現のための完全開発ワークフロー。majiayu000plan-mode-arc-gsm8k-improvementAEGISモデルのARC-Challenge評価改善とGSM8K健全性チェックのためのPlanモード。タイムアウト率・抽出失敗率分析、頑健な回答抽出、データ汚染検査、複数seed評価を実行。majiayu000plan-mode-official-leaderboard-abctest公式リーダーボード準拠のA/B/Cテストを実行するPlanモードスキル。Phi-3.5-mini-instruct、Borea-phi3.5-instinct-jp、AEGIS-Phi3.5mini-jpv2.4を標準化ベンチマークで比較評価し、統計的有意性を…majiayu000plan-researchResearch a problem space with evidence gathering and source validationmajiayu000plan-researchResearch a problem space with evidence gathering and source validation.majiayu000master-planner-researcher-prpMaster planner + deep researcher. Use when you need to turn a request into a research-backed, implementation-ready plan (PRP)…majiayu000planning-patternsStructured planning methodology with research, brainstorming, phased plan creation, risk assessment, and plan-to-build continuity.a5c-aiwritesplot-structureThis skill should be used when the user asks to "create a plot arc", "story structure", "add a plot point", "story timeline"…majiayu000plot-workflowOrchestrate and coordinate one-click generation workflow for major plot points and detailed plot points. Suitable for structured…majiayu000writespm-organization-task-researchCodebase research specialist for PM task assignment. Use proactively before assigning tasks to understand existing patterns…majiayu000poet-analystAnalyzes events through poetic lens using close reading, metaphor analysis, imagery, rhythm, form analysis, and attention to…majiayu000complexity-analyzerAnalyzes task/feature complexity (1-10) and recommends subtask breakdown for planning and prioritization. Provides actionable…majiayu000power-agent-creatorThis skill should be used when users want to create powerful AI agents comparable to Claude Code or sonph-code. It provides…majiayu000ppw:experimentAnalyze experiment results and generate discussion paragraphs for academic papers. Two-phase workflow: identify measurable…majiayu000Predictive Skill LoadingAnticipates and pre-loads optimal skills before task execution based on pattern matching and historical success ratesmajiayu000premortemAnalyze what could go wrong with a plan. Use when: - User asks "what could go wrong", "risks", "potential issues" - Before…majiayu000premortemPre-mortem analysis that imagines a plan has failed, then works backward to identify causes and preventions. Use before launches…majiayu000product-pairSuggest complementary products that pair well with a given item — side tables for sofas, task lights for desks, etc.majiayu000writesproject-awarenessComprehensive project context detection and state awareness. Use when relevant to the task.majiayu000project-note-json-to-epubConvert structured project-note JSON manuscripts into validated EPUB and optional Kindle-clickable PDF files. Use when the user…twhsiproject-time-tracker프로젝트별 Claude Code 세션 시간을 집계하여 리포트 생성. 일별/주별/월별 시간 분포를 Obsidian 테이블로 시각화. "시간 추적", "프로젝트 시간", "time tracking" 등의 요청 시 자동 적용.majiayu000prompt-builderBuild effective prompts for Claude Code skills. Creates clear, specific, actionable prompts using engineering principles…majiayu000writesprompt-engineeringInteractive prompt optimization workflow for LLMs. Use when optimizing, improving, or engineering prompts for Claude, GPT…majiayu000prompt-generatorGenerate optimized Claude Code prompts for any request. This is the main entry point for the prompt generation system. Use this…majiayu000prompt-level-selectionGuide selection of appropriate prompt level for a task. Use when choosing between simple prompts and complex workflows, applying…majiayu000proof-skeleton-generatorGenerate structured proof skeletons with tactics, strategies, and intermediate lemmas for theorems in Isabelle/HOL or Coq. Use…majiayu000publication-trustAssess the scientific integrity and trustworthiness of publications before relying on their findings. Use this skill whenever…majiayu000py-config-botExecute BioETL py-config-bot profile for role-specific workflow and constraints.majiayu000py-plan-botExecute BioETL py-plan-bot profile for role-specific workflow and constraints.majiayu000python-background-jobsPython background job patterns including task queues, workers, and event-driven architecture. Use when implementing async task…wshobsonqiskitComprehensive quantum computing toolkit for building, optimizing, and executing quantum circuits. Use when working with quantum…majiayu000
← Prev15 / 244Next →
How the catalog works
What is an agent skill?

A folder with a SKILL.md inside — instructions, and often scripts and assets, that an AI agent loads when the task matches. Claude Code, Codex, Cursor and Copilot all read the same format, so one skill usually works across them.

Where does this catalog come from?

We read 660 source repositories straight from their file trees rather than from submitted listings — what you see is what is actually published. 98 repositories were rejected because they advertise skills but contain none: link lists, not folders.

Why is there no install counter?

Because install counts live in the registry that serves `npx skills add`, and that is not ours — publishing a number we cannot verify would be worse than showing none. Instead we show where a skill comes from and whether attention around its source is actually growing, measured from our own weekly snapshots.

Do you deduplicate?

Yes, and it matters more than expected. Aggregator repositories republish the same skill in several places — one source carried 6,317 SKILL.md files for 2,001 actual skills. We collapse by folder name and keep the canonical copy, so the catalog counts things, not copies.

Keep going